{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YQDHX53Q43KIZ4HT5YV3YNOT6F","short_pith_number":"pith:YQDHX53Q","schema_version":"1.0","canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","source":{"kind":"arxiv","id":"2412.14446","version":2},"attestation_state":"computed","paper":{"title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric M. Wolff, Gregory P. Meyer, Siddhartha Srinivasa, Siva Karthik Mustikovela, Xin Huang, Yi Xu, Yuxin Hu, Zaiwei Zhang","submitted_at":"2024-12-19T01:53:36Z","abstract_excerpt":"Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.14446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T01:53:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b69c3b5ae8fdec6d92bfe52bfa0a5aa8c7ef630f6fecb7c3a644d0ae8e53821","abstract_canon_sha256":"061a997b0d7da33ba78b8a7a2f5aceefaf2038d277bd1792152de0ae272bb6b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:56.709106Z","signature_b64":"LxJgqrQ7ql8uQTmRw3RqbeEUFz45O4OV5QppaSXfpaPYxStng3ytZ51V4axqah47/OI8Lrg8OAnboueVruhXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4067bf770e6d48cf0f3ee2bbc35d3f177ed4d284c972b250fb70429fcc60681","last_reissued_at":"2026-07-05T12:01:56.708613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:56.708613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric M. Wolff, Gregory P. Meyer, Siddhartha Srinivasa, Siva Karthik Mustikovela, Xin Huang, Yi Xu, Yuxin Hu, Zaiwei Zhang","submitted_at":"2024-12-19T01:53:36Z","abstract_excerpt":"Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14446","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.14446/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.14446","created_at":"2026-07-05T12:01:56.708666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14446v2","created_at":"2026-07-05T12:01:56.708666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14446","created_at":"2026-07-05T12:01:56.708666+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQDHX53Q43KI","created_at":"2026-07-05T12:01:56.708666+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQDHX53Q43KIZ4HT","created_at":"2026-07-05T12:01:56.708666+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQDHX53Q","created_at":"2026-07-05T12:01:56.708666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22617","citing_title":"OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21337","citing_title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09919","citing_title":"Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28570","citing_title":"Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29425","citing_title":"ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15925","citing_title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21747","citing_title":"Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20082","citing_title":"VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00088","citing_title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19710","citing_title":"SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08266","citing_title":"Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F","json":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F.json","graph_json":"https://pith.science/api/pith-number/YQDHX53Q43KIZ4HT5YV3YNOT6F/graph.json","events_json":"https://pith.science/api/pith-number/YQDHX53Q43KIZ4HT5YV3YNOT6F/events.json","paper":"https://pith.science/paper/YQDHX53Q"},"agent_actions":{"view_html":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F","download_json":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F.json","view_paper":"https://pith.science/paper/YQDHX53Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14446&json=true","fetch_graph":"https://pith.science/api/pith-number/YQDHX53Q43KIZ4HT5YV3YNOT6F/graph.json","fetch_events":"https://pith.science/api/pith-number/YQDHX53Q43KIZ4HT5YV3YNOT6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/action/storage_attestation","attest_author":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/action/author_attestation","sign_citation":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/action/citation_signature","submit_replication":"https://pith.science/pith/YQDHX53Q43KIZ4HT5YV3YNOT6F/action/replication_record"}},"created_at":"2026-07-05T12:01:56.708666+00:00","updated_at":"2026-07-05T12:01:56.708666+00:00"}